© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73115
    Prev
    Next
    INDEX
    Explanations

    class constructors and initializers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ╽
    -2.02
    ˿
    -1.96
     ofere
    -1.84
    鱟
    -1.83
    archiwizowane
    -1.81
    粜
    -1.76
    ⃙
    -1.75
     sözler
    -1.73
     obiet
    -1.73
     detayl
    -1.73
    POSITIVE LOGITS
    0
    2.95
    6
    2.80
    3
    2.61
    .
    2.50
    8
    2.48
    7
    2.45
    1
    2.44
    4
    2.42
    5
    2.36
    :
    2.30
    Activations Density 0.004%

    No Known Activations